{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T03:54:09Z","timestamp":1742961249409,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031189067"},{"type":"electronic","value":"9783031189074"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-18907-4_57","type":"book-chapter","created":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:03:53Z","timestamp":1666825433000},"page":"735-748","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["BiTMulV: Bidirectional-Decoding Based Transformer with\u00a0Multi-view Visual Representation"],"prefix":"10.1007","author":[{"given":"Qiankun","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"XueKui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Chu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,27]]},"reference":[{"key":"57_CR1","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., Socher, R.: Knowing when to look: Adaptive attention via a visual sentinel for image captioning. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 375\u2013383 (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"57_CR2","doi-asserted-by":"crossref","unstructured":"Revaud, J., Almaz\u00e1n, J., Rezende, R.S., Souza, C.R.D.: Learning with average precision: Training image retrieval with a listwise loss. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5107\u20135116 (2019)","DOI":"10.1109\/ICCV.2019.00521"},{"key":"57_CR3","doi-asserted-by":"crossref","unstructured":"Chen, C., Liu, Y., Kreiss, S., Alahi, A.: Crowd-robot interaction: Crowd-aware robot navigation with attention-based deep reinforcement learning. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 6015\u20136022 (2019)","DOI":"10.1109\/ICRA.2019.8794134"},{"key":"57_CR4","doi-asserted-by":"crossref","unstructured":"Fox, E.A., Ingram, W.A.: Introduction to digital libraries. In: Proceedings of the ACM\/IEEE Joint Conference on Digital Libraries in 2020, pp. 567\u2013568 (2020)","DOI":"10.1145\/3383583.3398501"},{"key":"57_CR5","doi-asserted-by":"crossref","unstructured":"Sen, S., Gupta, K.K., Ekbal, A., Bhattacharyya, P.: Multilingual unsupervised NMT using shared encoder and language-specific decoders. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 3083\u20133089 (2019)","DOI":"10.18653\/v1\/P19-1297"},{"key":"57_CR6","doi-asserted-by":"crossref","unstructured":"Chen, C., Mu, S., Xiao, V., Ye, Z., Wu, V., Ju, Q.: Improving image captioning with conditional generative adversarial nets. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 8142\u20138150 (2019)","DOI":"10.1609\/aaai.v33i01.33018142"},{"key":"57_CR7","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: A neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"57_CR8","unstructured":"Xu, K., et al.: Show, attend and tell: Neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"57_CR9","unstructured":"Yang, Y., Teo, C.L., Daum$$\\acute{\\,}$$e III, H., Aloimonos, Y.: Corpus-guided sentence generation of natural images. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 444\u2013454 (2011)"},{"issue":"12","key":"57_CR10","doi-asserted-by":"publisher","first-page":"2891","DOI":"10.1109\/TPAMI.2012.162","volume":"35","author":"G Kilkarni","year":"2013","unstructured":"Kilkarni, G., et al.: Babytalk: understanding and generating simple image descriptions. IEEE Trans. Pattern Anal. Mach. Intell. 35(12), 2891\u20132903 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"57_CR11","doi-asserted-by":"crossref","unstructured":"Farhadi, A., et al.: Every picture tells a story: Generating sentences from images. In: European Conference on Computer Vision, pp. 15\u201329 (2010)","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"57_CR12","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"57_CR13","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Mei, T.: Exploring visual relationship for image captioning. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 684\u2013699 (2018)","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"57_CR14","doi-asserted-by":"crossref","unstructured":"Guo, L., Liu, J., Zhu, X., Yao, P., Lu, S., Lu, H.: Normalized and geometry-aware self-attention network for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10327\u201310336 (2020)","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"57_CR15","doi-asserted-by":"crossref","unstructured":"Pan, Y., Yao, T., Li, Y., Mei, T.: X-linear attention networks for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10971\u201310980 (2020)","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"57_CR16","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.Y.: Attention on attention for image captioning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4634\u20134643 (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"issue":"12","key":"57_CR17","doi-asserted-by":"publisher","first-page":"4467","DOI":"10.1109\/TCSVT.2019.2947482","volume":"30","author":"J Yu","year":"2019","unstructured":"Yu, J., Li, J., Yu, Z., Huang, Q.: Multimodal transformer with multi-view visual representation for image captioning. IEEE Trans. Circuits Syst. Video Technol. 30(12), 4467\u20134480 (2019)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"57_CR18","doi-asserted-by":"crossref","unstructured":"Liu, L., Utiyama, M., Finch, A., Sumita, E.: Agreement on target-bidirectional neural machine translation. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 411\u2013416 (2016)","DOI":"10.18653\/v1\/N16-1046"},{"key":"57_CR19","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1162\/tacl_a_00256","volume":"7","author":"L Zhou","year":"2019","unstructured":"Zhou, L., Zhang, J., Zong, C.: Synchronous bidirectional neural machine translation. Trans. Assoc. Comput. Linguist. 7, 91\u2013105 (2019)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"57_CR20","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Wu, S., Liu, S., Li, M., Zhou, M., & Xu, T.: Regularizing neural machine translation by target-bidirectional agreement. In Proceedings of the AAAI Conference on Artificial Intelligence, pp. 443\u2013450 (2019)","DOI":"10.1609\/aaai.v33i01.3301443"},{"key":"57_CR21","doi-asserted-by":"crossref","unstructured":"Wang, C., Yang, H., Meinel, C.: Image captioning with deep bidirectional LSTMs and multi-task learning. In: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 14(2s), 1\u201320 (2018)","DOI":"10.1145\/3115432"},{"key":"57_CR22","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7008\u20137024 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"57_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: Common objects in context. In European Conference on Computer Vision, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"57_CR24","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Qiu, Z., Mei, T.: Boosting image captioning with attributes. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4894\u20134902 (2017)","DOI":"10.1109\/ICCV.2017.524"},{"key":"57_CR25","doi-asserted-by":"crossref","unstructured":"Jiang, W., Ma, L., Jiang, Y. G., Liu, W., Zhang, T.: Recurrent fusion network for image captioning. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 499\u2013515 (2018)","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"57_CR26","doi-asserted-by":"crossref","unstructured":"Qin, Y., Du, J., Zhang, Y., Lu, H.: Look back and predict forward in image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8367\u20138375 (2019)","DOI":"10.1109\/CVPR.2019.00856"},{"key":"57_CR27","doi-asserted-by":"crossref","unstructured":"Yang, X., Tang, K., Zhang, H., Cai, J.: Auto-encoding scene graphs for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10685\u201310694 (2019)","DOI":"10.1109\/CVPR.2019.01094"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-18907-4_57","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:15:38Z","timestamp":1666826138000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-18907-4_57"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031189067","9783031189074"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-18907-4_57","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"27 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/en.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"microsoft","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"564","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"233","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"41% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.03","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.35","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}